© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 24667
    Prev
    Next
    INDEX
    Explanations

    terms related to gastrointestinal health and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    55
    +0.12
    0.7%
    492
    +0.12
    0.6%
    297
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.12
    0.01
    504
    +0.12
    0.00
    206
    +0.11
    0.01
    Negative Logits
    ĻĤ
    -2.79
    ¿½
    -2.58
    Ī
    -2.48
    ĸ
    -2.48
    į
    -2.35
    Ĥ¬
    -2.34
    Ŀ
    -2.31
    Ķ
    -2.29
    £
    -2.28
    ¤
    -2.22
    POSITIVE LOGITS
    osto
    1.59
    zing
    1.43
     elapsed
    1.36
    zes
    1.35
    ause
    1.35
    ostatic
    1.35
     Psychological
    1.34
    itar
    1.33
     repetitions
    1.32
    wagen
    1.32
    Activations Density 0.324%

    No Known Activations